From the School of Medicine (J.V.C., G.C.) and Department of Radiology and Biomedical Imaging (C.P.H., O.A.G., L.P.S., A.M.R., Y.L.), University of California, San Francisco, 505 Parnassus Avenue, M-391, San Francisco, CA 94143-0628.
Radiology. 2022 Dec;305(3):678-687. doi: 10.1148/radiol.211860. Epub 2022 Jul 19.
Background Assessment of appropriate brain myelination on T1- and T2-weighted MRI scans is based on gestationally corrected age (GCA) and requires subjective visual inspection of the brain with knowledge of normal myelination milestones. Purpose To develop a convolutional neural network (CNN) capable of estimating neonatal and infant GCA based on brain myelination on MRI scans. Materials and methods In this retrospective study from one academic medical center, brain MRI scans of patients aged 0-25 months with reported normal myelination were consecutively collected between January 1995 and June 2019. The GCA at MRI was manually calculated. After exclusion criteria were applied, T1- and T2-weighted MRI scans were preprocessed with skull stripping, linear registration, scoring for normalization, and downsampling. A three-dimensional regression CNN was trained to predict GCA using mean absolute error (MAE) as its loss function. Attention maps were calculated using layer-wise relevance propagation. Models were validated on an external test set from the National Institutes of Health (NIH). Model MAEs were compared using Kruskal-Wallis and Mann-Whitney tests. Results A total of 518 neonates and infants (mean GCA, 67 weeks ± 33 [SD], 56% male) was included, comprising 469 T1-, 438 T2-, and 389 T1- and T2-weighted studies. Across 10 runs, MAEs of T1-, T2-, and T1- and T2-weighted networks were 9.8 ± 2.3, 9.1 ± 1.9, and 7.7 ± 1.7 weeks, respectively. Attention map analysis demonstrated increased network attention to the cerebellum, posterior white matter, and basal ganglia signal in neonates with GCA of less than 40 weeks and the anterior white matter signal in infants with GCA of more than 120 weeks, corresponding to the known progression of myelination. The T1- and T2-weighted network tested on the external NIH test set had an MAE of 9.1 weeks, which was reduced to 5.9 weeks with further training using half the external test set ( < .001). Conclusion A three-dimensional convolutional neural network can predict the gestationally corrected age of neonates and infants aged 0-25 months based on brain myelination patterns on T1- and T2-weighted MRI scans. © RSNA, 2022
背景 在 T1 加权和 T2 加权 MRI 扫描上评估适当的脑髓鞘形成，需要基于校正胎龄（GCA）的主观视觉检查，并了解正常髓鞘形成的里程碑。目的 开发一种能够基于 MRI 扫描上的脑髓鞘形成来估计新生儿和婴儿 GCA 的卷积神经网络（CNN）。材料与方法 这是一项来自单一学术医疗中心的回顾性研究，连续收集了 1995 年 1 月至 2019 年 6 月期间报告正常髓鞘形成的 0-25 月龄患者的脑 MRI 扫描。MRI 时的 GCA 是手动计算的。应用排除标准后，对 T1 加权和 T2 加权 MRI 扫描进行颅骨剥离、线性配准、归一化评分和下采样预处理。使用均方误差（MAE）作为损失函数训练三维回归 CNN 以预测 GCA。使用层相关传播计算注意力图。使用 Kruskal-Wallis 和 Mann-Whitney 检验比较模型的 MAE。结果 共纳入 518 名新生儿和婴儿（平均 GCA 为 67 周±33[标准差]，56%为男性），包括 469 项 T1 加权、438 项 T2 加权和 389 项 T1 和 T2 加权研究。在 10 次运行中，T1、T2 和 T1 和 T2 加权网络的 MAE 分别为 9.8±2.3、9.1±1.9 和 7.7±1.7 周。注意力图分析表明，GCA<40 周的新生儿网络对小脑、后白质和基底节信号的关注度增加，GCA>120 周的婴儿对前白质信号的关注度增加，这与已知的髓鞘形成过程相对应。在外部 NIH 测试集上测试的 T1 和 T2 加权网络的 MAE 为 9.1 周，使用外部测试集的一半进行进一步训练后，MAE 降低至 5.9 周（<0.001）。结论 一种三维卷积神经网络可以基于 T1 加权和 T2 加权 MRI 扫描上的脑髓鞘形成模式来预测 0-25 月龄新生儿和婴儿的校正胎龄。
